Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668051b510ddefbb3696970a71406e3f1cd0f21aae397aceac4d818705969ae1
+oid sha256:9d58e6949a3d839a83a674d9e7045e8330ff3d573a89cf014a30ba75cf84ab51
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b818adc8bea35b29c070d1fd7e3fd1263fc7320b88eb8b5602f750f2ae71091f
-size 325339796
+oid sha256:724cc58cf8af01a2097c50fdf0041e72ccf78666b517d2687a16494e51ce1759
+size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab720254f5557cc24c31943b94b9826898477a59ea138dfef59404325b0a558d
+oid sha256:446b19ae8dc93b9c61634f6f392296f919b70aa5f9632e225edafb6e85361eb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335c5ad5d49110db61ad1b0e85277ad0de8eaa71b71c181fa25e7d8bd8f3fc98
+oid sha256:41439765e4324bfba55c134066121dc462eb56b67b27f6e7308aecd489d52c0e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0507456064224243,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.01629566861128312,
+  "best_metric": 0.9808639287948608,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.019554802333539744,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 14.466,
       "eval_steps_per_second": 3.616,
       "step": 250
+    },
+    {
+      "epoch": 0.016947495355734445,
+      "grad_norm": 2.0789878368377686,
+      "learning_rate": 0.00011487096017983597,
+      "loss": 0.8857,
+      "step": 260
+    },
+    {
+      "epoch": 0.01759932210018577,
+      "grad_norm": 1.4197766780853271,
+      "learning_rate": 0.00010762954765706012,
+      "loss": 0.903,
+      "step": 270
+    },
+    {
+      "epoch": 0.018251148844637095,
+      "grad_norm": 2.561424732208252,
+      "learning_rate": 0.00010037045234293992,
+      "loss": 0.9548,
+      "step": 280
+    },
+    {
+      "epoch": 0.01890297558908842,
+      "grad_norm": 1.98018217086792,
+      "learning_rate": 9.312903982016405e-05,
+      "loss": 1.1046,
+      "step": 290
+    },
+    {
+      "epoch": 0.019554802333539744,
+      "grad_norm": 5.7000837326049805,
+      "learning_rate": 8.594058952263925e-05,
+      "loss": 1.3285,
+      "step": 300
+    },
+    {
+      "epoch": 0.019554802333539744,
+      "eval_loss": 0.9808639287948608,
+      "eval_runtime": 446.8663,
+      "eval_samples_per_second": 14.456,
+      "eval_steps_per_second": 3.614,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.217183012696883e+16,
+  "total_flos": 6.248876759580672e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null